Automated detection, segmentation and measurement of major vessels and the trachea in CT pulmonary angiography
Abstract Mediastinal structure measurements are important for the radiologist’s review of computed tomography pulmonary angiography (CTPA) examinations. In the reporting process, radiologists make measurements of diameters, volumes, and organ densities for image quality assessment and risk stratific...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-45509-1 |
| _version_ | 1797647298413461504 |
|---|---|
| author | Ali T. Kahraman Tomas Fröding Dimitrios Toumpanakis Nataša Sladoje Tobias Sjöblom |
| author_facet | Ali T. Kahraman Tomas Fröding Dimitrios Toumpanakis Nataša Sladoje Tobias Sjöblom |
| author_sort | Ali T. Kahraman |
| collection | DOAJ |
| description | Abstract Mediastinal structure measurements are important for the radiologist’s review of computed tomography pulmonary angiography (CTPA) examinations. In the reporting process, radiologists make measurements of diameters, volumes, and organ densities for image quality assessment and risk stratification. However, manual measurement of these features is time consuming. Here, we sought to develop a time-saving automated algorithm that can accurately detect, segment and measure mediastinal structures in routine clinical CTPA examinations. In this study, 700 CTPA examinations collected and annotated. Of these, a training set of 180 examinations were used to develop a fully automated deterministic algorithm. On the test set of 520 examinations, two radiologists validated the detection and segmentation performance quantitatively, and ground truth was annotated to validate the measurement performance. External validation was performed in 47 CTPAs from two independent datasets. The system had 86–100% detection and segmentation accuracy in the different tasks. The automatic measurements correlated well to those of the radiologist (Pearson’s r 0.68–0.99). Taken together, the fully automated algorithm accurately detected, segmented, and measured mediastinal structures in routine CTPA examinations having an adequate representation of common artifacts and medical conditions. |
| first_indexed | 2024-03-11T15:15:16Z |
| format | Article |
| id | doaj.art-ee70ec89a31740dc8048c7bbbd6d34b3 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-11T15:15:16Z |
| publishDate | 2023-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-ee70ec89a31740dc8048c7bbbd6d34b32023-10-29T12:24:57ZengNature PortfolioScientific Reports2045-23222023-10-0113111210.1038/s41598-023-45509-1Automated detection, segmentation and measurement of major vessels and the trachea in CT pulmonary angiographyAli T. Kahraman0Tomas Fröding1Dimitrios Toumpanakis2Nataša Sladoje3Tobias Sjöblom4Department of Immunology, Genetics and Pathology, Uppsala UniversityDepartment of Radiology, Nyköping HospitalDepartment of Radiology, Uppsala University HospitalCentre for Image Analysis, Department of Information Technology, Uppsala UniversityDepartment of Immunology, Genetics and Pathology, Uppsala UniversityAbstract Mediastinal structure measurements are important for the radiologist’s review of computed tomography pulmonary angiography (CTPA) examinations. In the reporting process, radiologists make measurements of diameters, volumes, and organ densities for image quality assessment and risk stratification. However, manual measurement of these features is time consuming. Here, we sought to develop a time-saving automated algorithm that can accurately detect, segment and measure mediastinal structures in routine clinical CTPA examinations. In this study, 700 CTPA examinations collected and annotated. Of these, a training set of 180 examinations were used to develop a fully automated deterministic algorithm. On the test set of 520 examinations, two radiologists validated the detection and segmentation performance quantitatively, and ground truth was annotated to validate the measurement performance. External validation was performed in 47 CTPAs from two independent datasets. The system had 86–100% detection and segmentation accuracy in the different tasks. The automatic measurements correlated well to those of the radiologist (Pearson’s r 0.68–0.99). Taken together, the fully automated algorithm accurately detected, segmented, and measured mediastinal structures in routine CTPA examinations having an adequate representation of common artifacts and medical conditions.https://doi.org/10.1038/s41598-023-45509-1 |
| spellingShingle | Ali T. Kahraman Tomas Fröding Dimitrios Toumpanakis Nataša Sladoje Tobias Sjöblom Automated detection, segmentation and measurement of major vessels and the trachea in CT pulmonary angiography Scientific Reports |
| title | Automated detection, segmentation and measurement of major vessels and the trachea in CT pulmonary angiography |
| title_full | Automated detection, segmentation and measurement of major vessels and the trachea in CT pulmonary angiography |
| title_fullStr | Automated detection, segmentation and measurement of major vessels and the trachea in CT pulmonary angiography |
| title_full_unstemmed | Automated detection, segmentation and measurement of major vessels and the trachea in CT pulmonary angiography |
| title_short | Automated detection, segmentation and measurement of major vessels and the trachea in CT pulmonary angiography |
| title_sort | automated detection segmentation and measurement of major vessels and the trachea in ct pulmonary angiography |
| url | https://doi.org/10.1038/s41598-023-45509-1 |
| work_keys_str_mv | AT alitkahraman automateddetectionsegmentationandmeasurementofmajorvesselsandthetracheainctpulmonaryangiography AT tomasfroding automateddetectionsegmentationandmeasurementofmajorvesselsandthetracheainctpulmonaryangiography AT dimitriostoumpanakis automateddetectionsegmentationandmeasurementofmajorvesselsandthetracheainctpulmonaryangiography AT natasasladoje automateddetectionsegmentationandmeasurementofmajorvesselsandthetracheainctpulmonaryangiography AT tobiassjoblom automateddetectionsegmentationandmeasurementofmajorvesselsandthetracheainctpulmonaryangiography |